© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10972
    Prev
    Next
    INDEX
    Explanations

    conditional statements and scenarios involving user actions or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "If" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.83
     دیکھیے
    -0.76
    AddHtmlAttribute
    -0.73
    expandindo
    -0.67
    ensement
    -0.66
    ArgsConstructor
    -0.65
     Normdatei
    -0.65
    awtextra
    -0.61
     تضيفلها
    -0.61
     onPostExecute
    -0.60
    POSITIVE LOGITS
     really
    0.68
     prefer
    0.62
    really
    0.61
     REALLY
    0.59
     particularly
    0.57
     option
    0.56
    ECT
    0.55
    Really
    0.55
    そこまで
    0.55
     Really
    0.54
    Activations Density 0.273%

    No Known Activations